Study of Uplink Resource Allocation for 5G IoT Services by Using Reinforcement Learning

Yen Wen Chen, Cheng Yu Tsai

Research output: Contribution to journalArticlepeer-review


In order to support real time IoT services, the ultra Reliable and Low Latency Communications (uRLLC) was proposed in 5G wireless communication network. Different from the grant based access in 4G, the grant free technique is proposed in 5G to reduce the random access delay of uRLLC-required applications. This paper proposes the dedicated resource for exclusive access of individual UE and the shared resource pool for the contention of multiple UEs by adopting the reinforcement learning approach. The objective of this paper is to accomplish the uplink successful rate above 99.9% under certain transmission error probability. The proposed Prediction based Hybrid Resource Allocation (PHRA) scheme allocates the access resource in a heuristic manner by referring to the activity of UEs. The dedicated resource is mainly allocated to the high activity UEs and the initial transmission of UEs with medium activity while the shared resource pool is allocated for the re-transmission of medium activity UEs and low activity UEs by using the reinforcement learning model. The burst traffic model was applied during the exhaustive experiments. And the simulation results show that the proposed scheme achieves higher uplink packet delivery ratio and more effective resource utilization than the other schemes.

Original languageEnglish
Pages (from-to)675-681
Number of pages7
JournalJournal of Internet Technology
Issue number3
StatePublished - 2023


  • 5G wireless communications
  • Internet of things
  • Random access
  • Resource allocation
  • uRLLC


Dive into the research topics of 'Study of Uplink Resource Allocation for 5G IoT Services by Using Reinforcement Learning'. Together they form a unique fingerprint.

Cite this